Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to driving forces and motivations behind actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    drive, driving, drove

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nakalista
    -0.34
    coroutines
    -0.34
    дарт
    -0.34
    ✤
    -0.33
     pretend
    -0.32
     actionMode
    -0.31
    〗
    -0.31
     conta
    -0.31
     gọn
    -0.31
     remb
    -0.30
    POSITIVE LOGITS
     drive
    1.10
     driving
    1.03
    Driving
    1.01
    drive
    0.96
     Drive
    0.95
     DRIVE
    0.94
     drives
    0.94
     drove
    0.93
     Driving
    0.93
    Drive
    0.92
    Act Density 0.009%

    No Known Activations